ai-memory — Persistent Memory for Any AI

Name: ai-memory — Persistent Memory for Any AI
Author: alphaonedev

@alphaonedev

关于 ai-memory — Persistent Memory for Any AI

Persistent memory for any AI assistant. Zero token cost until recall. Stores memories locally in SQLite, ranks by 6-factor scoring, returns results in TOON compact format (79% smaller than JSON). 17 MCP tools, 20 HTTP endpoints, 25 CLI commands. 4 tiers from keyword to autonomous

#mcp #memory #ai #sqlite #rust #llm #embeddings #vector-search #cli #knowledge-management #local-first #open-source #claude #chatgpt #cursor #ollama

基本信息

分类

记忆与知识

传输方式

stdio

发布者

alphaonedev

提交者

AlphaOne

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "memory": {
      "command": "ai-memory",
      "args": [
        "--db",
        "~/.claude/ai-memory.db",
        "mcp",
        "--tier",
        "semantic"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is ai-memory?

ai-memory is a persistent memory system for AI assistants that uses zero context tokens until recall. It returns only relevant memories using six-factor scoring and TOON format, reducing response size by 79% compared to JSON. It is designed for use with multiple AI platforms including Claude, Codex, Gemini, and others.

How to use ai-memory?

Install ai-memory via cargo install ai-memory. Then use its 17 MCP tools such as memory_store, memory_recall, memory_search, and memory_list. The default tier is semantic; you can switch to keyword, smart (with Ollama), or autonomous (with Ollama) as needed.

Key features of ai-memory

Zero token cost until memory_recall is called
TOON format responses are 79% smaller than JSON
Six

记忆与知识分类下的更多 MCP 服务器

Rust Docs MCP Server

Govcraft

🦀 Prevents outdated Rust code suggestions from AI assistants. This MCP server fetches current crate docs, uses embeddings/LLMs, and provides accurate context via a tool call.

286